© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 12406
    Prev
    Next
    INDEX
    Explanations

    JSON, code, lists, punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    isVideoRecording
    0.44
    endif
    0.41
    return
    0.40
     কারণ
    0.38
    }$\
    0.38
    कक्ष
    0.38
     drained
    0.38
    ুখে
    0.37
     endif
    0.37
    বাবুর
    0.37
    POSITIVE LOGITS
    、（
    0.37
    胱
    0.37
    ，
    0.37
     हाउ
    0.36
     Cómo
    0.36
     Hé
    0.35
    瑪
    0.35
     Backyard
    0.35
     ö
    0.35
    ్రహ
    0.35
    Activations Density 0.055%

    No Known Activations